diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 73c57b327793..5cb64f454e69 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -241,6 +241,9 @@ full:L40S/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ full:L40S/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_multi_instance[MMLU] SKIP (https://nvbugs/6649818) full:L40S/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_tp_pp_symmetric[GSM8K-tp1pp2] SKIP (https://nvbugs/6649818) full:L40S/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_tp_pp_symmetric[MMLU-tp1pp2] SKIP (https://nvbugs/6649818) +full:L40S/accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp2pp2-attn_backend=FLASHINFER-torch_compile=False] SKIP (https://nvbugs/6689016) +full:L40S/accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp2pp2-attn_backend=FLASHINFER-torch_compile=True] SKIP (https://nvbugs/6689016) +full:L40S/accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[tp2pp2-fp8kv=False-attn_backend=FLASHINFER-torch_compile=False] SKIP (https://nvbugs/6689016) full:L40S/disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_attention_dp_overlap[DeepSeek-V3-Lite-fp8] SKIP (https://nvbugs/6581064) full:L40S/disaggregated/test_disaggregated.py::test_disaggregated_logprobs_serving[llama-3.1-8b-instruct] SKIP (https://nvbugs/6275959) full:RTXPro6000D/accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_cutlass-torch_compile=True] SKIP (https://nvbugs/5929339)